INDEX

Explanations

specific instances or examples of something within a context or category

oai_token-act-pair · gpt-3.5-turbo

references to various cases or instances related to investigations or events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ople

-0.77

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.61

ousands

-0.60

 Concord

-0.59

ructose

-0.59

Gameplay

-0.58

 Clubs

-0.57

adena

-0.56

\<

-0.55

 Registry

-0.55

POSITIVE LOGITS

worldly

1.01

 besides

0.95

 unrelated

0.86

 outing

0.84

 altogether

0.81

bender

0.72

 installment

0.72

roller

0.67

addon

0.67

 avenue

0.67

Activations Density 0.249%

specific instances or examples of something within a context or category

references to various cases or instances related to investigations or events

No Comments

No Known Activations